Two-stage Autoencoder Neural Network for 3D Speech Enhancement.
Han YinJisheng BaiSiwei HuangMou WangYafei JiaJianfeng ChenPublished in: CoRR (2023)
Keyphrases
- speech enhancement
- neural network
- noise reduction
- noisy environments
- single channel
- signal to noise ratio
- speech signal
- pattern recognition
- smoothing algorithm
- back propagation
- linear prediction
- wiener filter
- vocal tract
- multiresolution
- speech recognition
- multi channel
- hidden layer
- image quality
- graphical models
- edge detection